Multi-camera collision detection between known and unknown objects

Today, real-time collision detection is a basic demand for many applications. While collision tests between known (modeled) objects have been around for quite a while, collision detection of known objects with dynamic, unknown (sensor-detected) objects remains a challenging field of research, especially when it comes to real-time requirements. The collision test described in this paper is based on several stationary, calibrated video cameras, each supervising the entire 3-dimensional space shared by unknown and known objects (e.g. humans and robots). Based on their images, potential collisions of the known objects in any of their (future) configurations with a priori unknown dynamic obstacles are detected. Occlusions caused by known objects (such as the robot or machinery set-up within the workspace) are detected and addressed in a safe manner by exploiting the geometrical information of the known objects and the epipolar line geometry of the calibrated cameras in a decision fusion process. The algorithm can be parameterized to adapt to different application demands. Experimental validation shows that real-time behaviour is possible in the presence of highly dynamic unknown obstacles as they occur when humans and robots share the same workspace for the accomplishment of a shared task. In effect, the vision-based collision test can safely be used for human-robot cooperation, intrusion detection, velocity damping, or obstacle avoidance.

[1]  Stefan Thiemermann.  Direkte Mensch-Roboter-Kooperation in der Kleinteilemontage mit einem SCARA-Roboter , 2005 .

[2]  Dominik Henrich,et al.  SIMERO: Camera Supervised Workspace for Service Robots , 2004 .

[3]  Gerald Eckert.  Automatic shape reconstruction of rigid 3-D objects from multiple calibrated images , 2000, 2000 10th European Signal Processing Conference.

[4]  Dominik Henrich,et al.  Modeling Intuitive behavior for safe human/robot coexistence cooperation , 2006, Proceedings 2006 IEEE International Conference on Robotics and Automation, 2006. ICRA 2006..

[5]  W. Niem.  Error Analysis for Silhouette – Based 3 D Shape Estimation from Multiple Views , 1997 .

[6]  Dominik Henrich,et al.  Safe human-robot-cooperation: image-based collision detection for industrial robots , 2002, IEEE/RSJ International Conference on Intelligent Robots and Systems.

[7]  S. Thiemermann,et al.  Direkte Mensch-Roboter Kooperation in einer flexiblen Montagezelle , 2002 .

[8]  Dominik Henrich,et al.  Velocity control for safe robot guidance based on fused vision and force/torque data , 2006, 2006 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems.

[9]  Andreas Meisel,et al.  3-D-Bildverarbeitung für feste und bewegte Kameras , 1994 .

[10]  Dominik Henrich,et al.  Safe human-robot-cooperation: problem analysis, system concept and fast sensor fusion , 2001, Conference Documentation International Conference on Multisensor Fusion and Integration for Intelligent Systems. MFI 2001 (Cat. No.01TH8590).

[11]  Jin-Jang Leou,et al.  Robot operation monitoring for collision avoidance by image sequence analysis , 1992, Pattern Recognit..

[12]  Badrinath Roysam,et al.  Image change detection algorithms: a systematic survey , 2005, IEEE Transactions on Image Processing.

[13]  Jean-Claude Latombe,et al.  Robot motion planning , 1970, The Kluwer international series in engineering and computer science.

[14]  Ian D. Walker,et al.  Sensor network based workcell for industrial robots , 2001, Proceedings 2001 IEEE/RSJ International Conference on Intelligent Robots and Systems. Expanding the Societal Role of Robotics in the the Next Millennium (Cat. No.01CH37180).

[15]  Dominik Henrich,et al.  SIMERO: Sichere Mensch-Roboter-Koexistenz , 2003 .

[16]  Peter Eisert,et al.  Automatic reconstruction of stationary 3-D objects from multiple uncalibrated camera views , 2000, IEEE Trans. Circuits Syst. Video Technol..

[17]  Andreas Bischoff.  Echtzeit Kollisionsvermeidung für einen Industrieroboter durch 3D-Sensorüberwachung , 1999 .

[18]  Dirk Ebert.  Bildbasierte Erzeugung kollisionsfreier Transferbewegungen für Industrieroboter , 2003, Schriftenreihe / Fachbereich Informatik, Universität Kaiserslautern.

[19]  Masatoshi Ishikawa,et al.  Safe human-robot-coexistence: emergency-stop using a high-speed vision-chip , 2005, 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[20]  Dominik Henrich,et al.  Human-robot cooperation: safe pick-and-place operations , 2005, ROMAN 2005. IEEE International Workshop on Robot and Human Interactive Communication, 2005..

[21]  Dominik Henrich,et al.  Multi-Camera Collision Detection allowing for Object Occlusions , 2006 .

[22]  O. Schulz,et al.  Image-based 3D-surveillance in man-robot-cooperation , 2004, 2nd IEEE International Conference on Industrial Informatics, 2004. INDIN '04. 2004.